CN114463165A

CN114463165A - Method and device for determining VOI (volume of interest)

Info

Publication number: CN114463165A
Application number: CN202111144575.7A
Authority: CN
Inventors: 苟天昌; 闫浩; 李金升
Original assignee: Our United Corp
Current assignee: Our United Corp
Priority date: 2021-09-28
Filing date: 2021-09-28
Publication date: 2022-05-10

Abstract

The application discloses a VOI (Voice over Internet protocol) determining method and device, and belongs to the technical field of medical image processing. The VOI determination method comprises the following steps: acquiring M target point cloud points, wherein M is a positive integer; determining M projection points of the cloud points of the M target points on a target projection surface, wherein the target projection surface is as follows: one of the three projection surfaces is vertical to each other, and the intersection point is the central point of the regular VOI; the target projection surface comprises an irregular target projection area; determining a target projection point located in the target projection area from the M projection points; and determining a target VOI according to the point cloud point corresponding to the target projection point.

Description

Method and device for determining VOI (volume of interest)

Technical Field

The application belongs to the technical field of medical image processing, and particularly relates to a VOI (volume-in-view) determining method and device.

Background

At present, point cloud data corresponding to an outer contour of a human body may be collected by a three-dimensional (3D) camera, then a volume of interest (VOI) including a plurality of point cloud data to be registered is determined by a user operation, and finally point cloud data in the regular VOI and point cloud data in a reference template are registered.

However, since a large number of point cloud points interfering with the registration are included in the regular VOI, this results in poor accuracy of the registration.

Disclosure of Invention

The embodiment of the application aims to provide a VOI (volume in-process) determining method and device, which can solve the problem of poor accuracy of point cloud registration of point cloud data.

In a first aspect, an embodiment of the present application provides a VOI determining method, where the method includes: acquiring M target point cloud points, wherein M is a positive integer; determining M projection points of the cloud points of the M target points on a target projection surface, wherein the target projection surface is as follows: one of the three projection surfaces is vertical to each other, and the intersection point is the central point of the regular VOI; the target projection surface comprises an irregular target projection area; determining a target projection point positioned in the target projection area from the M projection points; and determining a target VOI according to the point cloud point corresponding to the target projection point.

In a second aspect, an embodiment of the present application provides a VOI determination apparatus, where the VOI determination apparatus includes: the device comprises an acquisition module, a first determination module, a second determination module and a third determination module. The acquisition module is used for acquiring M target point cloud points, wherein M is a positive integer. A first determining module, configured to determine M projection points on a target projection surface among the M target point cloud points acquired by the acquiring module, where the target projection surface is: one of the three projection surfaces is vertical to each other, and the intersection point is the central point of the regular VOI; the target projection surface includes an irregular target projection area. And the second determining module is used for determining the target projection point positioned in the target projection area from the M projection points determined by the first determining module. And the third determining module is used for determining the target VOI according to the point cloud point corresponding to the target projection point determined by the second determining module.

In a third aspect, embodiments of the present application provide a computer device, which includes a processor, a memory, and a program or instructions stored on the memory and executable on the processor, and when executed by the processor, implement the steps of the method according to the first aspect.

In a fourth aspect, embodiments of the present application provide a readable storage medium, on which a program or instructions are stored, which when executed by a processor implement the steps of the method according to the first aspect.

In a fifth aspect, an embodiment of the present application provides a chip, where the chip includes a processor and a communication interface, where the communication interface is coupled to the processor, and the processor is configured to execute a program or instructions to implement the method according to the first aspect.

In this embodiment of the application, the VOI determining apparatus may first obtain M target point cloud points, determine M projection points of the M target point cloud points on an irregular target projection plane of three projection planes, where the three projection planes are perpendicular to each other and an intersection point is a central point of a regular VOI, then determine a target projection point located in a target projection area from the M projection points, and determine the target VOI according to a point cloud point corresponding to the target projection point. Because the target projection surface comprises the irregular target projection area, a large number of point cloud points which interfere registration cannot be introduced into the target VOI determined by the projection points of the M target point cloud points on the irregular target projection surface and positioned in the target projection area, and the registration accuracy is improved.

Drawings

Fig. 1 is a schematic diagram of a VOI determination method provided in an embodiment of the present application;

fig. 2 is a second schematic diagram of a VOI determination method according to an embodiment of the present application;

fig. 3 is a third schematic diagram of a VOI determination method provided by an embodiment of the present application;

fig. 4 is a fourth schematic diagram of a VOI determination method provided by an embodiment of the present application;

fig. 5 is a fifth schematic diagram of a VOI determination method provided by an embodiment of the present application;

fig. 6 is a sixth schematic diagram of a VOI determination method provided by an embodiment of the present application;

fig. 7 is a seventh schematic diagram of a VOI determination method provided by an embodiment of the present application;

FIG. 8 is a schematic illustration of a plurality of point clouds in an embodiment of the application;

FIG. 9 is a schematic diagram of an initial VOI in an embodiment of the present application;

FIG. 10 is a schematic diagram of Y point cloud points in an embodiment of the present application;

FIG. 11 is a schematic diagram of three binary maps in an embodiment of the present application;

FIG. 12 is a schematic diagram of a target VOI in an embodiment of the present application;

fig. 13 is a schematic structural diagram of a VOI determination apparatus according to an embodiment of the present application;

fig. 14 is a schematic structural diagram of a computer device provided in an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be described clearly below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments that can be derived by one of ordinary skill in the art from the embodiments given herein are intended to be within the scope of the present disclosure.

The terms first, second and the like in the description and in the claims of the present application are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that embodiments of the application may be practiced in sequences other than those illustrated or described herein, and that the terms "first," "second," and the like are generally used herein in a generic sense and do not limit the number of terms, e.g., the first term can be one or more than one. In addition, "and/or" in the specification and claims means at least one of connected objects, a character "/" generally means that a preceding and succeeding related objects are in an "or" relationship.

The VOI determination method provided by the embodiment of the present application is described in detail below with reference to the accompanying drawings by specific embodiments and application scenarios thereof.

The VOI determination method provided by the application can be applied to a scene of point cloud matching. For example, in radiation treatment of a patient, in order to reduce adverse effects of involuntary patient movement on the radiation treatment results, a monitoring device, such as a 3D camera, is typically provided to monitor patient movement before or during radiation treatment.

When the head of a patient is subjected to radiotherapy, the patient can be fixed in a non-invasive positioning mode (such as a mask positioning mode), but the head of the patient still can slightly move in a mask during a positioning stage before the radiotherapy or during the radiotherapy, so that the radiotherapy precision is affected. When the head of a patient is monitored by using a 3D camera, point cloud data corresponding to a regular VOI selected from the acquired contour data of the head of the patient (e.g., a large number of point cloud points in the regular VOI in fig. 9) is usually registered with a reference template (including only the face of the patient and not including point cloud points of the mask of the patient), however, the regular VOI includes a large number of point cloud points (also called outer points or interference points) corresponding to the mask except for the part to be monitored, in addition to the point cloud points including the face of the patient to be monitored, which reduces the accuracy of the registration.

Therefore, the embodiment of the application provides a VOI determination method, which can be applied to a VOI determination device and can extract an irregular VOI of a part to be monitored. As shown in fig. 1, the VOI determination method provided in the embodiment of the present application may include steps 101 to 104 described below.

Step 101, obtaining M target point cloud points.

In the embodiment of the application, M is a positive integer.

It can be understood that the M target point cloud points may include point cloud data corresponding to a target to be monitored, and the target to be monitored includes a part to be monitored. The object to be monitored may be a patient, or a phantom, etc., and the part to be monitored may be a part on the object to be monitored, such as a head, a body, etc.

Here, the VOI determining apparatus may acquire M target cloud points from the medical imaging instrument; wherein the medical imaging instrument may comprise at least one of: 3D cameras, passive binocular depth cameras, time-of-flight depth cameras, lidar depth cameras, and the like.

And 102, determining M projection points of the cloud points of the M target points on the target projection surface.

In an embodiment of the present application, the target projection plane is: and one of the three projection surfaces is vertical to each other, the intersection point is the central point of the regular VOI, each target point cloud point corresponds to one projection point, and the target projection surface comprises an irregular target projection area.

Here, the regular VOI may be a default VOI, a VOI determined according to the M target cloud points, or a VOI determined by a user. The regular VOI may have a cubic shape, such as a BOX shape shown in fig. 9, i.e., a regular hexahedral shape, but may have other shapes, which is not particularly limited in the embodiments of the present application.

And 103, determining a target projection point in the target projection area from the M projection points.

In the embodiment of the present application, after the VOI determining apparatus determines M projection points, a target projection point located in a target projection area is determined from the M projection points.

The target projection area may be a preset area on the target projection surface, or an area determined by a predetermined algorithm or rule.

And step 104, determining a target VOI according to the point cloud point corresponding to the target projection point.

In this embodiment, the VOI determining apparatus may determine the target VOI according to the point cloud point corresponding to the target projection point, where the target VOI is generally an irregular VOI.

According to the VOI determination method provided by the embodiment of the application, the VOI determination device can firstly acquire M target point cloud points, and determine M projection points of the M target point cloud points on an irregular target projection surface in three projection surfaces, wherein the three projection surfaces are mutually vertical, and the intersection point is the central point of a regular VOI, then determine a target projection point in a target projection area from the M projection points, and determine the target VOI according to the point cloud point corresponding to the target projection point. Because the target projection surface comprises the irregular target projection area, a large number of point cloud points which interfere registration cannot be introduced into the target VOI determined by the projection points of the M target point cloud points on the irregular target projection surface and positioned in the target projection area, and the registration accuracy is improved.

In this embodiment, with reference to fig. 1, as shown in fig. 2, before step 101, the VOI determining method provided in this embodiment may further include step 201 and step 202 described below.

Step 201, a plurality of cloud points of the target to be monitored are obtained.

The VOI determining apparatus may obtain a plurality of cloud points of the target to be monitored from the medical imaging instrument, where the plurality of cloud points may be understood as: at least two point cloud points, i.e. two or more point cloud points.

Here, the M target cloud points may specifically be: some of the plurality of point cloud points.

Step 202, determining M target point cloud points located in the regular VOI from the plurality of point cloud points of the target to be monitored.

The VOI determining means may determine, for each of the plurality of point cloud points, whether a distance from one point cloud point to each of the three projection surfaces is less than or equal to a preset value to determine whether the one point cloud point is located within the regular VOI, and in a case where the one point cloud point is determined to be located within the regular VOI, the VOI determining means may determine the one point cloud point as one target point cloud point to determine the M target point cloud points. Here, the preset value may be half the length, width and height of the regular VOI.

In the embodiment of the present application, if a point cloud point is located in the regular VOI, the point cloud point may be considered as a point cloud point required by the user, that is, an interior point, and therefore, the VOI determining apparatus may determine the point cloud point as a target point cloud point.

Therefore, the VOI determining device can determine M target point cloud points located in the regular VOI from the plurality of acquired point cloud points, and then determine the point cloud points required by the user based on the M target point cloud points, so that the VOI determining device can determine the accurate target VOI according to the point cloud points required by the user, and therefore the accuracy of point cloud registration of point cloud data can be improved.

Optionally, in this embodiment, with reference to fig. 1, as shown in fig. 3, before step 101, the VOI determining method provided in this embodiment may further include step 301 described below.

And 301, acquiring a target projection surface.

Here, the target projection plane is: a default projection plane of the three projection planes, or a projection plane determined by the VOI determination device.

Optionally, in this embodiment of the application, with reference to fig. 3, as shown in fig. 4, the step 301 may be specifically implemented by the following steps 301a to 301 d.

And 301a, acquiring Y point cloud points forming an irregular target to be monitored.

In the embodiment of the present application, the Y point cloud points are located in a regular VOI, and Y is a positive integer.

Here, the VOI determining apparatus may display M target point cloud points first, so that the user may input a part of the M target point cloud points, so that the VOI determining apparatus may acquire Y point cloud points from the part of the point cloud points.

And 301b, acquiring a projection point set of the Y point cloud points on each projection plane in the three projection planes.

In the embodiment of the present application, a projection point set corresponding to a projection plane includes: y projection points of the Y point cloud points on one projection plane.

For example, after the VOI determining means determines a VOI (i.e., an initial VOI in the following embodiments), the VOI determining means may determine Y point cloud points according to user input on some of the M target point cloud points.

For example, as shown in fig. 10, the VOI determining apparatus may determine, according to the user input to some of the M target cloud points, Y cloud points from the M target cloud points (it should be noted that the Y cloud points are illustrated by Y white points in the figure).

Here, for each of the three projection surfaces, the VOI determining apparatus may first determine Y cloud points, Y projection points on one projection surface to obtain one projection point set corresponding to the one projection surface, and determine each projection point set corresponding to each projection surface.

For example, for each of the Y point cloud points, the VOI determining apparatus may determine, according to three-dimensional coordinate information of one point cloud point and a plane equation of one projection plane, three-dimensional coordinate information of one projection point of the one point cloud point on the one projection plane to obtain the one projection point, to obtain Y projection points on the one projection plane to obtain a projection point set of the Y point cloud point on the one projection plane.

And step 301c, determining three projection areas according to the three projection point sets.

In the embodiment of the present application, each of the three projection regions is: and projecting the Y projection points in one projection point set to the area formed by the corresponding projection surface.

For each of the three projection point sets, the VOI determining apparatus may obtain the two-dimensional coordinate information of each projection point according to the three-dimensional coordinate information of each projection point in one projection point set by using a PCA dimension reduction method, and thus the VOI determining apparatus may generate a closed projection region according to the two-dimensional coordinate information of each projection point to obtain one projection region, so as to obtain three projection regions.

And step 301d, determining the projection area with the largest area among the three projection areas as a target projection area, and determining a projection surface corresponding to the target projection area as a target projection surface.

After the VOI determining device determines the three projection regions, the VOI determining device may process each of the three projection regions by using a region growing method (or a connected component extracting method) to obtain three binary maps, so that the VOI determining device may determine, according to the three binary maps, a projection region with a largest region area among the three projection regions to determine the target projection plane, and thus the VOI determining device may acquire the target projection plane.

It should be noted that, for the description of the "region generation method (or connected domain extraction method)", reference may be made to specific descriptions in the related art, and details are not repeated herein in the embodiments of the present application.

Illustratively, for each of the three binary images, one binary image includes one target region, and one target region corresponds to one projection region.

For example, the VOI determining apparatus may determine, from the three binary maps, one binary map with the largest area of the target region, and then determine a projection region corresponding to the one binary map as the projection region with the largest area.

For example, the VOI determining apparatus may perform processing on each projection region of the three projection regions by using a region growing method, as shown in fig. 11, to obtain three binary maps, where a first binary map includes a target region (e.g., region 10), a second binary map includes another target region (e.g., region 11), and a third binary map includes yet another target region (e.g., region 12), so that the VOI determining apparatus may determine, from the three binary maps, a binary map (e.g., a third binary map) in which the region area of the target region is the largest (i.e., region 12), then determine the projection region corresponding to the third binary map as the projection region having the largest region area, determine the projection region (i.e., the projection region corresponding to the third binary map) as the target projection region, and determine the projection plane corresponding to the target projection region, and determining the target projection surface.

Optionally, in this embodiment of the present application, the rule VOI is: determined according to the M target cloud points or determined according to the input of a user.

Here, in the case where the regular VOI is determined based on the M target cloud points, the VOI determining apparatus may determine the initial VOI by a regular VOI determining method according to the M target cloud points, and determine the regular VOI according to the initial VOI.

It should be noted that, for the description of the "regular VOI determination method", reference may be made to specific descriptions in the related art, and details of the embodiments of the present application are not repeated herein.

Optionally, in this embodiment of the present application, the regular VOI is determined according to an input from a user. Specifically, with reference to fig. 4, as shown in fig. 5, before step 301b, the VOI determining method provided in the embodiment of the present application may further include step 401 and step 402 described below.

Step 401, obtaining X key points located outside a plurality of cloud points of a target to be monitored.

In the embodiment of the application, X is a positive integer which is greater than or equal to 4.

Here, the X key points may be vertices of the initial VOI, or key points determined according to an input of a user.

Specifically, under the condition that the X key points are determined according to the input of the user, the VOI determining apparatus may display a plurality of point cloud points on the display screen, so that the user may click and input a part of point cloud points outside the plurality of point cloud points, so that the VOI determining apparatus may obtain the X key points outside the plurality of point cloud points of the target to be monitored according to the input parameter of the second input.

Wherein the input parameters of the second input may include at least one of: input location, input trajectory, etc.

For example, in the case that the input parameter of the second input is an input position, the VOI determining apparatus may determine a keypoint corresponding to the input position of each sub-input as one keypoint to determine X keypoints.

And step 402, determining three projection surfaces according to the X key points.

Therefore, the VOI determining device can acquire at least four key points positioned outside the plurality of cloud points of the target to be monitored, and accurately determine the three projection surfaces according to the at least four key points so as to accurately determine the target VOI according to the accurate three projection surfaces, so that the accuracy of point cloud registration of point cloud data can be improved.

Alternatively, in this embodiment of the application, the step 402 may be specifically implemented by the following steps 402a to 402 c.

Step 402a, determining the target centers corresponding to the X key points.

In the embodiment of the present application, the target center is: the center of the circumscribed sphere of the X key points.

Illustratively, the target center may specifically be: the smallest of the X keypoints circumscribes the center of the sphere.

In this embodiment, the VOI determining apparatus may determine, based on the three-dimensional coordinate information of the X key points, the three-dimensional coordinate information of the target center corresponding to the X key points, so as to determine the target center.

It should be noted that, for the description of determining, by the VOI determining apparatus, the three-dimensional coordinate information of the target center corresponding to the key point based on the three-dimensional coordinate information of the key point, reference may be made to specific descriptions in the related art, and details of the embodiment of the present application are not repeated herein.

And 402b, respectively determining target coordinate information corresponding to each key point according to the coordinate information of each key point in the X key points and the coordinate information of the target center.

It can be understood that the coordinate information of each key point in the X key points is three-dimensional coordinate information, the coordinate information of the target center is three-dimensional coordinate information, and the target coordinate information corresponding to each key point is three-dimensional coordinate information.

The VOI determination device can determine target coordinate information corresponding to one key point according to a difference value between three-dimensional coordinate information of one key point and three-dimensional coordinate information of a target center so as to determine target coordinate information corresponding to each key point.

It can be understood that the target coordinate information corresponding to each key point is the decentralized three-dimensional coordinate information of each key point.

And step 402c, determining three projection surfaces according to the X target coordinate information.

Therefore, the VOI determining device can determine the decentralized target coordinate information of each key point according to the center of the external sphere of the X key points, so as to accurately determine the three projection surfaces according to the target coordinate information corresponding to each key point, and accordingly the VOI determining device can determine the accurate regular VOI based on the decentralized target coordinate information of the X key points and the accurate three projection surfaces, and therefore the accuracy of point cloud data point cloud registration can be improved.

Optionally, in this embodiment of the application, the step 402c may be specifically implemented by the following steps 402c1 to 402c 3.

And step 402c1, constructing an object matrix with X rows and three columns according to the X object coordinate information.

Here, for each of the X pieces of object coordinate information, the VOI determining means may determine the coordinate value in one direction in one piece of object coordinate information as one element of a row, and determine the coordinate value in another direction in the one piece of object coordinate information as another element of the row, and so on until the coordinate value in the last direction in the one piece of object coordinate information is determined as the last element of the row to obtain three columns and one row of the object matrix to construct the object matrix of three columns and X rows.

And step 402c2, determining three eigenvalues and three eigenvectors after the transposition matrix of the target matrix is multiplied by the target matrix.

In the embodiment of the present application, each of the three feature vectors is a normal vector of each projection plane.

Here, the three feature values correspond to the three feature vectors one to one.

And step 402c3, determining three projection surfaces according to the three eigenvalues, the three eigenvectors and the plane equation in the three-dimensional space.

Here, the VOI determining apparatus may sequence the three feature values according to a target sequence, substitute a feature vector corresponding to a first feature value of the sequenced three feature values into a plane equation in the three-dimensional space to obtain a plane equation of a first projection plane, substitute a feature vector corresponding to a second feature value into a plane equation in the three-dimensional space to obtain a plane equation of a second projection plane, substitute a feature vector corresponding to a third feature value into a plane equation in the three-dimensional space to obtain a plane equation of a third projection plane to obtain a plane equation of the third projection plane, and determine the three projection planes.

Wherein, the target sequence may be: in order of small to large, or in order of large to small.

Illustratively, assume three eigenvalues as eigenvalues D₁Characteristic value D₂And a characteristic value D₃，D₁＜D₂＜D₃The three eigenvectors include eigenvalues D₁Corresponding feature vectors, e.g. feature vector { A₁，B₁，C₁}, and a characteristic value D₂Corresponding feature vectors, e.g. feature vector { A₂，B₂，C₂}, and a characteristic value D₃Corresponding feature vectors, e.g. feature vector { A₃，B₃，C₃Thus, the VOI determining means may first pair the characteristic values D in a target order (e.g., in a small-to-large order)₁Characteristic value D₂And a characteristic value D₃Sorting the first eigenvalue (namely eigenvalue D)₁) Corresponding feature vector { A₁，B₁，C₁Substituting the plane equation in the three-dimensional space, wherein Ax + By + Cz + D is 0, and obtaining the plane equation of the first projection plane, namely a₁x+B₁y+C₁z + D is 0 to determine the first projection plane, and the second eigenvalue (i.e., eigenvalue D)₂) Corresponding feature vector { A₂，B₂，C₂Substituting the equation into a plane equation in three-dimensional space, wherein Ax + By + Cz + D is 0, and obtaining a plane equation of a second projection plane, namely a₂x+B₂y+C₂z + D is 0 to determine the second projection plane, and the third eigenvalue (i.e. eigenvalue D)₃) Corresponding feature vector { A₃，B₃，C₃Substituting the equation into a plane in three-dimensional space, where Ax + By + Cz + D is 0, to obtain a plane equation of a third projection plane, i.e., a₃x+B₃y+C₃z + D is 0 to determine the third projection plane and thus the three projection planes.

Therefore, the VOI determining device can construct a target matrix according to X target coordinate information, and determine three eigenvalues and three eigenvectors according to the target matrix and the transpose matrix of the target matrix, so that the VOI determining device can accurately determine three projection planes according to the three eigenvalues, the three eigenvectors and a plane equation in a three-dimensional space.

Optionally, in this embodiment of the application, with reference to fig. 5, as shown in fig. 6, after the step 402, the VOI determining method provided in this embodiment of the application may further include the following step 501.

Step 501, determining a regular VOI according to the X key points and the three projection surfaces.

Here, after the VOI determining means determines the regular VOI, the regular VOI may be displayed so that the user may select Y point cloud points located within the regular VOI.

Alternatively, in this embodiment of the application, the step 501 may be specifically implemented by the following steps 501a to 501 c.

Step 501a, a first distance between each key point of the X key points and the first projection plane is respectively determined.

In an embodiment of the present application, the first projection plane is: any one of the three projection surfaces.

For each key point in the X key points, the VOI determining apparatus may determine, according to the target coordinate information corresponding to the key point and the plane equation of the first projection plane, a first distance between the key point and the first projection plane, to determine X first distances.

Step 501b, determining a first size parameter of the regular VOI according to a maximum distance of the X first distances.

In an embodiment of the present application, the first dimension parameter is: any one of the three target size parameters.

The VOI determining means may determine the first size parameter based on a maximum distance of the X first distances and a preset constant.

For example, in this embodiment of the application, the VOI determining apparatus may obtain one parameter according to a product of a maximum distance of the X first distances and a preset constant, and determine the one parameter as the first size parameter.

Exemplarily, assuming that the maximum distance among the X first distances is a and the preset constant is 2, the VOI determining apparatus may determine 2a as the first size parameter.

Step 501c, determining a regular VOI based on the three target size parameters.

The VOI determining apparatus may determine the three target size parameters as size parameters in one direction of the regular VOI, respectively, with a center point (i.e., a preset center point) of the initial VOI as a center, to obtain the regular VOI.

Exemplarily, assuming that the three target size parameters include a size parameter 1, a size parameter 2, and a size parameter 3, the VOI determining means may determine the size parameter 1 as a size parameter in one direction of the regular VOI, for example, as a length of the regular VOI, and the size parameter 2 as a size parameter in another direction of the regular VOI, for example, as a width of the regular VOI, centering on a center point of the initial VOI, and determine the size parameter 3 as a size parameter in yet another direction of the regular VOI, for example, as a height of the regular VOI, to obtain the regular VOI.

In the embodiment of the application, the VOI determining device may obtain a distance between each key point of the X key points and each projection plane, and determine one size parameter of the regular VOI according to a maximum distance in the distances, respectively, to obtain three target size parameters, so that the VOI determining device may determine the regular VOI according to the three target size parameters.

Therefore, the VOI determining device can determine one size parameter according to the maximum distance in the distance between each key point and each projection plane to determine three target size parameters, and thus, the VOI determining device can accurately determine the regular VOI according to the three target size parameters, so that the VOI determining device can determine M projection points according to the accurate regular VOI, and therefore, the accuracy of point cloud registration of point cloud data can be improved.

It should be noted that, in the VOI determination method provided in the embodiment of the present application, the execution subject may be a VOI determination apparatus, or a control module in the VOI determination apparatus for executing the VOI determination method. In the embodiment of the present application, a VOI determination apparatus executing a VOI determination method is taken as an example, and the VOI determination apparatus provided in the embodiment of the present application is described.

To more clearly illustrate the technical solution of the present application, a detailed example of a VOI determination method applied to a VOI determination apparatus is given below, which can extract an irregular VOI of a portion to be monitored. As shown in fig. 7, the VOI determination method provided in this embodiment of the present application may include two stages:

the first stage, determining the target projection surface of the target to be monitored, as in steps 601 to 606; in the second stage, after the target projection surface of the target to be monitored is determined, a template to be registered, i.e., a target VOI, of the target to be monitored is determined by using the target projection surface in the actual positioning or radiotherapy process, for example, in steps 607 to 611, so that the point cloud point corresponding to the target VOI is used as the template and compared with the point cloud point of the target to be monitored acquired in real time, and the monitoring of the target to be monitored in the positioning or radiotherapy process can be realized.

For the first stage:

step 601, obtaining a plurality of cloud points of the target to be monitored.

Here, the VOI determining apparatus may acquire point cloud points (or contour points) of the object to be monitored using a 3D camera to acquire a plurality of point cloud points of the object to be monitored, which are used to extract an irregular VOI for registration in the object to be monitored, as shown in fig. 8. Here, the object to be monitored may be a patient wearing a mask.

It should be noted that the phantom in fig. 8 to 12 indicates the actual patient.

Step 602, obtaining a plurality of cloud points of a part to be monitored of a target to be monitored.

Since some point cloud points that are not part to be monitored (e.g., head) exist in the acquired point cloud points of the target to be monitored, the VOI determining apparatus needs to remove the point cloud points of the part that is not to be monitored. Therefore, the VOI determining apparatus may generate and display an initial VOI covering the part to be monitored of the target to be monitored and excluding the part not to be monitored, and then acquire a plurality of cloud points of the part to be monitored of the target to be monitored within the initial VOI.

As shown in fig. 9, in the BOX-type VOI of the initial VOI in this example, the user may manually adjust the position of the initial VOI, for example, drag the center point of the initial VOI, and the user may also adjust the size of the initial VOI, for example, drag the end points of three mutually perpendicular line segments that pass through the preset center point on the initial VOI, and adjust the sizes of the initial VOI in different directions.

The initial VOI may be a VOI generated by default by the VOI determining apparatus as a BOX type VOI, or may be a regular VOI determined according to X key points input by a user, where the X key points are points located outside a plurality of cloud points of a part to be monitored of the object to be monitored, and X is a positive integer greater than or equal to 4.

It should be noted that the initial VOI is not necessarily parallel to three coordinate axes of a coordinate system where a plurality of cloud points of the target to be monitored are located, and may be a regular VOI rotated around any coordinate axis, but the initial VOI is in a BOX type.

Step 603, obtaining X key points outside the plurality of cloud points of the part to be monitored of the target to be monitored.

Here, the X key points are key points that determine the initial VOI, and in the case where the initial VOI is a default generated VOI in a BOX type, the X key points are 8 vertices of the initial VOI.

And step 604, determining three projection surfaces according to the X key points.

Alternatively, in this embodiment of the present application, the step 604 may be implemented by the following steps 604a to 604 c.

And step 604a, determining target centers corresponding to the X key points.

Here, the VOI determining means may calculate the target center from coordinate information (e.g., three-dimensional coordinate information) of the X key points.

And step 604b, determining target coordinate information corresponding to each key point according to the coordinate information of each key point in the X key points and the coordinate information of the target center.

Here, the coordinate information may specifically be three-dimensional coordinate information, and for each key point in the X key points, the VOI determining device may subtract the three-dimensional coordinate information of the target center from the coordinate information of one key point to obtain target coordinate information corresponding to the one key point, so as to obtain target coordinate information corresponding to each key point.

And step 604c, determining three projection surfaces according to the X target coordinate information.

Alternatively, in this embodiment, the step 604c may be specifically implemented by the following steps 604c1 to 604c 3.

And step 604c1, constructing an object matrix with X rows and three columns according to the X object coordinate information.

For example, it is assumed that X pieces of target coordinate information are X pieces of three-dimensional coordinate information, so that the VOI determining apparatus can construct a target matrix of X rows and three columns from the X pieces of three-dimensional coordinate information.

And step 604c2, determining three eigenvalues and three eigenvectors after the transposition matrix of the target matrix is multiplied by the target matrix.

And step 604c3, determining three projection surfaces according to the three eigenvalues, the three eigenvectors and the plane equation in the three-dimensional space.

Here, the VOI determining apparatus may sequence the three feature values according to a target sequence, and then substitute a feature vector corresponding to a first feature value of the sequenced three feature values into a plane equation in the three-dimensional space to obtain a plane equation of a first projection plane, substitute a feature vector corresponding to a second feature value into a plane equation in the three-dimensional space to obtain a plane equation of a second projection plane, and so on until a plane equation of a third projection plane is obtained to determine the three projection planes.

Illustratively, assume three eigenvalues as eigenvalues D₁Characteristic value D₂And a characteristic value D₃，D₁＜D₂＜D₃The three eigenvectors include eigenvalues D₁Corresponding feature vector { A₁，B₁，C₁}, characteristic value D₂Corresponding feature vector { A₂，B₂，C₂And a feature value D₃Corresponding feature vector { A₃，B₃，C₃Thus, the VOI determining means may first apply the eigenvalues D in a target order (e.g., small to large order)₁Characteristic value D₂And a characteristic value D₃Sorting the first eigenvalue (namely eigenvalue D)₁) Corresponding feature vector { A₁，B₁，C₁Substituting the plane equation in the three-dimensional space, Ax + By + Cz + D ═ 0, to obtain the plane equation of the first projection plane, i.e., a₁x+B₁y+C₁z + D is 0 to determine the first projection plane, and the second eigenvalue (i.e., eigenvalue D)₂) Corresponding feature vector { A₂，B₂，C₂Substituting the equation into a plane equation in three-dimensional space, wherein Ax + By + Cz + D is 0, and obtaining a plane equation of a second projection plane, namely a₂x+B₂y+C₂z + D is 0 to determine the secondA projection plane, and a third feature value (i.e., feature value D)₃) Corresponding feature vector { A₃，B₃，C₃Substituting the equation into a plane in three-dimensional space, where Ax + By + Cz + D is 0, to obtain a plane equation of a third projection plane, i.e., a₃x+B₃y+C₃z + D is 0 to determine the third projection plane and thus the three projection planes.

And step 605, determining a regular VOI according to the X key points and the three projection planes.

It is to be understood that the VOI determining means may update the initial VOI to a regular VOI and display the regular VOI.

Alternatively, in this embodiment of the application, the step 605 may be specifically implemented by the following steps 605a to 605 c.

Step 605a, determining a first distance between each of the X key points and the first projection plane, respectively.

In the embodiment of the present application, the first projection plane is: any one of the three projection surfaces.

Here, the VOI determining means may determine the first distance between each key point and the first projection plane respectively according to the target coordinate information corresponding to each key point and the plane equation of the first projection plane to determine X first distances.

Step 605b, determining a first size parameter of the regular VOI according to a maximum distance of the X first distances.

In the embodiment of the present application, the first dimension parameter is: any one of the three target size parameters.

Here, the VOI determining means may determine the first size parameter as twice as large as a maximum distance of the X first distances.

Step 605c, determining the regular VOI based on the three target size parameters.

The VOI determining device may determine the three target size parameters as size parameters in one direction of the regular VOI, respectively, with a center point (i.e., a preset center point) of the initial VOI as a center, to obtain the regular VOI, and display the regular VOI.

And step 606, obtaining a target projection surface.

Alternatively, in this embodiment of the application, the step 606 may be specifically implemented by the following steps 606a to 606 d.

And 606a, acquiring Y point cloud points forming an irregular target to be monitored.

In the embodiment of the application, the Y point cloud points are located in the regular VOI, and Y is a positive integer.

In one example, a user manually selects P irregular cloud points (the region of the patient part which is customized by the user and does not contain the mask) for the part to be monitored of the target to be monitored, and then performs interpolation to obtain Y cloud points, where P is smaller than Y.

It can be understood that the area enclosed by the cloud points of the Y points is: the part of the patient to be monitored.

For example, as shown in fig. 10, the user manually inputs P point cloud points, surrounds the part of the patient of interest exposed outside the mask, including the eyes, the nose, and the like, interpolates the P point cloud points by using an interpolation algorithm, inserts more point cloud points, connects the Y point cloud points into a line to form a contour line surrounding the part of interest, and it should be noted that the Y point cloud points are indicated by Y white dots in the figure.

And step 606b, acquiring a projection point set of the Y point cloud points on each projection plane in the three projection planes.

Step 606c, determining three projection areas according to the three projection point sets.

It should be noted that, for the description of the PCA dimension reduction method, reference may be made to specific descriptions in related technologies, and details of the embodiments of the present application are not repeated herein.

Step 606d, determining the projection area with the largest area among the three projection areas as a target projection area, and determining the projection surface corresponding to the target projection area as a target projection surface.

For example, the VOI determining apparatus may perform processing on each projection region of the three projection regions by using a region growing method, as shown in fig. 11, to obtain three binary maps, where the first binary map includes a target region (e.g., region 10), the second binary map includes another target region (e.g., region 11), and the third binary map includes yet another target region (e.g., region 12), so that the VOI determining apparatus may determine, from the three binary maps, a binary map (e.g., a third binary map) in which the region area of the target region is the largest (i.e., region 12), then determine the projection region corresponding to the third binary map as the projection region having the largest region area, and determine the projection region (e.g., the projection region corresponding to the third binary map) as the target projection region, and determine the projection plane corresponding to the target projection region, and determining the target projection surface.

Aiming at the second stage:

and step 607, acquiring a plurality of cloud points of the target to be monitored.

Here, the VOI determining apparatus may acquire point cloud points (or contour points) of the object to be monitored again using the 3D camera to acquire a plurality of point cloud points of the object to be monitored again.

Step 608, determining M target point cloud points located in the regular VOI from the plurality of point cloud points of the target to be monitored.

Here, the VOI determining means may determine, for each of the plurality of point cloud points, whether a distance of one point cloud point to each of the three projection surfaces is less than or equal to a preset value to determine whether the one point cloud point is located within the regular VOI, and in a case where it is determined that the one point cloud point is located within the regular VOI, the VOI determining means may determine the one point cloud point as one target point cloud point to determine the M target point cloud points.

Here, the preset value is half the length, width and height of the regular VOI.

And step 609, determining M projection points of the cloud points of the M target points on the target projection surface.

In the embodiment of the present application, the target projection plane is: one of the three projection surfaces is vertical to each other, and the intersection point is the central point of the regular VOI; the target projection surface includes an irregular target projection area.

And step 610, determining a target projection point located in the target projection area from the M projection points.

Here, the VOI determining means may determine the target projected point located in the target projection area from the M projected points based on the two-dimensional coordinate information of the M projected points.

Specifically, the VOI determining apparatus may determine the target projection point from the M projection points according to the two-dimensional coordinate information of the M projection points and the binary map in which the area of the target region is the largest.

For example, in this embodiment of the application, in a case that the target projection point includes a plurality of projection points, for each projection point of the M projection points, the VOI determining device may determine, according to two-dimensional coordinate information of one projection point, a corresponding pixel point from one binary image with a largest area, and then determine, in a case that a gray value of the pixel point is 1, the one projection point as one projection point of the plurality of projection points, so as to determine the plurality of projection points (i.e., the target projection point).

And 611, determining the target VOI according to the point cloud points corresponding to the target projection points.

Here, the VOI determining means may generate the target VOI from the point cloud points corresponding to the target projection points to determine the target VOI.

For example, as shown in fig. 12, the VOI determining apparatus may determine the target VOI according to the point cloud point corresponding to the target projection point (it should be noted that the figure is illustrated by a shaded area).

According to the VOI determining method provided by the embodiment of the application, because the target projection surface comprises the irregular target projection area, a large number of point cloud points interfering registration cannot be introduced into the target VOI determined by the projection points of the M target point cloud points positioned in the target projection area on the irregular target projection surface, and the registration accuracy is improved.

Fig. 13 shows a schematic diagram of a possible structure of the VOI determining apparatus according to the embodiment of the present application. As shown in fig. 13, the VOI determining apparatus 60 may include: an acquisition module 61, a first determination module 62, a second determination module 63 and a third determination module 64.

The obtaining module 61 is configured to obtain M target point cloud points, where M is a positive integer.

A first determining module 61, configured to determine M projection points of the M target point cloud points acquired by the acquiring module 61 on a target projection surface, where the target projection surface is: one of the three projection surfaces is vertical to each other, and the intersection point is the central point of the regular VOI; the target projection surface includes an irregular target projection area. And a second determining module 62, configured to determine a projection point of the object located in the projection area of the object from the M projection points determined by the first determining module 61. And a third determining module 63, configured to determine the target VOI according to the point cloud point corresponding to the target projection point determined by the second determining module 62.

In a possible implementation manner, the obtaining module 61 is further configured to obtain a plurality of cloud points of the target to be monitored. The VOI determination apparatus 60 provided in the embodiment of the present application may further include: and a fourth determination module. The fourth determining module is configured to determine, from the multiple cloud points of the target to be monitored acquired by the acquiring module 61, M target point cloud points located in the regular VOI.

In a possible implementation manner, the above-mentioned obtaining module 61 is further configured to obtain the target projection plane.

In a possible implementation manner, the obtaining module 61 is specifically configured to obtain Y point cloud points forming an irregular target to be monitored, where the Y point cloud points are located in a regular VOI, and Y is a positive integer; and acquiring a projection point set of the Y point cloud points on each projection plane in the three projection planes, wherein the projection point set corresponding to one projection plane comprises: y projection points of the Y point cloud points on one projection plane. The VOI determining apparatus 60 provided in the embodiment of the present application may further include: and a fifth determining module. The fifth determining module is configured to determine three projection regions according to the three projection point sets, where each projection region is: projecting Y projection points in one projection point set to a region formed by corresponding projection surfaces; and determining the projection area with the largest area in the three projection areas as a target projection area, and determining the projection surface corresponding to the target projection area as a target projection surface.

In a possible implementation manner, the obtaining module 61 is further configured to obtain X key points located outside multiple cloud points of the object to be monitored, where X is a positive integer greater than or equal to 4. The VOI determining apparatus 60 provided in the embodiment of the present application may further include: and a sixth determining module. The sixth determining module is configured to determine three projection planes according to the X key points acquired by the acquiring module 61.

In a possible implementation manner, the sixth determining module is specifically configured to determine a target center corresponding to the X key points, where the target center is: the centers of the circumscribed spheres of the X key points; respectively determining target coordinate information corresponding to each key point according to the coordinate information of each key point in the X key points and the coordinate information of the target center; and determining three projection surfaces according to the X target coordinate information.

In a possible implementation manner, the sixth determining module is specifically configured to construct an object matrix with X rows and three columns according to X pieces of object coordinate information; determining three eigenvalues and three eigenvectors after multiplying the transposed matrix of the target matrix and the target matrix, wherein each eigenvector is a normal vector of each projection surface; and determining three projection surfaces according to the three eigenvalues, the three eigenvectors and a plane equation in the three-dimensional space.

In a possible implementation manner, the VOI determining apparatus 60 provided in an embodiment of the present application may further include: and a seventh determining module. And the seventh determining module is used for determining the regular VOI according to the X key points and the three projection surfaces.

In a possible implementation manner, the seventh determining module is specifically configured to determine a first distance between each of the X key points and a first projection plane, where the first projection plane is: any one of the three projection surfaces; and determining a first size parameter of the regular VOI according to a maximum distance of the X first distances, the first size parameter being: any one of the three target size parameters; and determining a regular VOI based on the three target size parameters.

The VOI determining apparatus provided in the embodiment of the application may obtain M target point cloud points first, determine M projection points of the M target point cloud points on an irregular target projection plane of three projection planes, where the three projection planes are perpendicular to each other and an intersection point is a central point of a regular VOI, then determine a target projection point located in a target projection area from the M projection points, and determine the target VOI according to a point cloud point corresponding to the target projection point. Because the target projection surface comprises the irregular target projection area, a large number of point cloud points which interfere registration cannot be introduced into the target VOI determined by the projection points of the M target point cloud points on the irregular target projection surface and positioned in the target projection area, and the registration accuracy is improved.

The above modules may be functional modules or program modules, and may be implemented by software or hardware. For a module implemented by hardware, the above modules may be located in the same processor; or the modules can be respectively positioned in different processors in any combination.

In addition, the VOI determination method described in conjunction with fig. 1 to 7 in the embodiment of the present application may be implemented by a computer device, that is, the VOI determination apparatus may be a computer device. Fig. 14 is a hardware configuration diagram of a computer device in one embodiment.

The computer device may include a processor 71, a memory 72 storing computer program instructions, and a program or instructions stored on the memory 72 and executable on the processor 71.

Specifically, the processor 71 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

Memory 72 may include, among other things, mass storage for data or instructions. By way of example, and not limitation, memory 72 may include a Hard Disk Drive (HDD), a floppy disk drive, a Solid State Drive (SSD), flash memory, an optical disk, a magneto-optical disk, tape, or a Universal Serial Bus (USB) drive or a combination of two or more of these. Memory 72 may include removable or non-removable (or fixed) media, where appropriate. The memory 72 may be internal or external to the data processing apparatus, where appropriate. In a particular embodiment, the memory 72 is a non-volatile (non-volatile) memory. In particular embodiments, memory 72 includes read-only memory (ROM) and Random Access Memory (RAM). Where appropriate, the ROM may be mask-programmed ROM, Programmable ROM (PROM), Erasable PROM (EPROM), Electrically Erasable PROM (EEPROM), Electrically Alterable ROM (EAROM), or FLASH memory (FLASH), or a combination of two or more of these. The RAM may be a Static Random Access Memory (SRAM) or a Dynamic Random Access Memory (DRAM), where the DRAM may be a Fast Page Mode Dynamic Random Access Memory (FPMDRAM), an Extended Data Out Dynamic Random Access Memory (EDODRAM), a Synchronous Dynamic Random Access Memory (SDRAM), and the like, where appropriate.

The memory 72 may be used to store or cache various data files that need to be processed and/or used for communication, as well as possible computer program instructions executed by the processor 71.

The processor 71 may implement any of the VOI determination methods in the above embodiments by reading and executing computer program instructions stored in the memory 72.

In some of these embodiments, the computer device may also include a communication interface 73 and a bus 70. As shown in fig. 14, the processor 71, the memory 72, and the communication interface 73 are connected via the bus 70 to complete mutual communication.

The communication interface 73 is used for realizing communication among modules, devices, units and/or equipment in the embodiment of the present application. The communication port 73 may also enable communication with other components such as: the data communication is carried out among external equipment, image/data acquisition equipment, a database, external storage, an image/data processing workstation and the like.

The bus 70 comprises hardware, software, or both that couple the components of the computer device to one another. Bus 70 includes, but is not limited to, at least one of the following: data bus (databus), address bus (address bus), control bus (control bus), expansion bus (expansion bus), and local bus (local bus). By way of example and not limitation, bus 70 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industrial Standard Architecture (EISA) bus, a front-side bus (FSB), a Hyper Transport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, a wireless bandwidth (infiniband) interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-express (PCI-X) bus, a serial advanced technology attachment (vldpa) bus, a local electronics association (SATA) bus, a video electronics standard association (video association) bus, or a combination of two or more of these buses, as appropriate. Bus 70 may include one or more buses, where appropriate. Although specific buses are described and shown in the embodiments of the application, any suitable buses or interconnects are contemplated by the application.

The computer device may execute the VOI determination method in the embodiment of the present application based on the acquired computer instruction, thereby implementing the VOI determination method described in conjunction with fig. 1 to 7.

An embodiment of the present application further provides a readable storage medium, where a program or an instruction is stored on the readable storage medium, and when the program or the instruction is executed by a processor, the program or the instruction implements each process of the foregoing VOI determination method embodiment, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here.

Wherein, the processor is the processor in the computer device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and the like. Here, the computer-readable storage medium may be a nonvolatile storage medium or a volatile storage medium.

The embodiment of the present application further provides a chip, where the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run a program or an instruction to implement each process of the above-mentioned embodiment of the VOI determination method, and can achieve the same technical effect, and in order to avoid repetition, the details are not repeated here.

It should be understood that the chips mentioned in the embodiments of the present application may also be referred to as a system-on-chip, or a system-on-chip.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Further, it should be noted that the scope of the methods and apparatus of the embodiments of the present application is not limited to performing the functions in the order illustrated or discussed, but may include performing the functions in a substantially simultaneous manner or in a reverse order based on the functions involved, e.g., the methods described may be performed in an order different than that described, and various steps may be added, omitted, or combined. In addition, features described with reference to certain examples may be combined in other examples.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a computer) to execute the methods according to the embodiments of the present application.

While the present embodiments have been described with reference to the accompanying drawings, it is to be understood that the invention is not limited to the precise embodiments described above, which are meant to be illustrative and not restrictive, and that various changes may be made therein by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.

Claims

1. A method for determining a volume of interest, VOI, the method comprising:

acquiring M target point cloud points, wherein M is a positive integer;

determining M projection points of the M target point cloud points on a target projection surface, wherein the target projection surface is as follows: one of the three projection surfaces is vertical to each other, and the intersection point is the central point of the regular VOI; the target projection surface comprises an irregular target projection area;

determining a target projection point located in the target projection area from the M projection points;

and determining a target VOI according to the point cloud point corresponding to the target projection point.

2. The method of claim 1, wherein prior to determining the M target point clouds of M projection points onto the target projection surface, the method further comprises:

acquiring a plurality of cloud points of a target to be monitored;

and determining M target point cloud points located in the regular VOI from the plurality of point cloud points of the target to be monitored.

3. The method of claim 1, wherein prior to the obtaining the M target cloud points, the method further comprises:

and acquiring the target projection surface.

4. The method of claim 3, wherein the acquiring the target projection surface comprises:

acquiring Y point cloud points forming an irregular target to be monitored, wherein the Y point cloud points are positioned in the regular VOI, and Y is a positive integer;

acquiring a projection point set of the Y point cloud points on each projection plane of the three projection planes, wherein the projection point set corresponding to one projection plane comprises: y projection points of the Y point cloud points on the projection surface;

determining three projection areas according to the three projection point sets, wherein each projection area is respectively as follows: projecting Y projection points in one projection point set to a region formed by corresponding projection surfaces;

and determining a projection area with the largest area in the three projection areas as a target projection area, and determining a projection plane corresponding to the target projection area as the target projection plane.

5. The method of claim 4, wherein the obtaining the set of projection points of the Y point cloud points on each of the three projection surfaces further comprises:

acquiring X key points which are positioned outside the plurality of cloud points of the target to be monitored, wherein X is a positive integer which is greater than or equal to 4;

and determining the three projection surfaces according to the X key points.

6. The method of claim 5, wherein said determining the three projection planes from the X keypoints comprises:

determining target centers corresponding to the X key points, wherein the target centers are as follows: the centers of the circumscribed spheres of the X key points;

respectively determining target coordinate information corresponding to each key point in the X key points according to the coordinate information of each key point and the coordinate information of the target center;

and determining the three projection surfaces according to the X target coordinate information.

7. The method of claim 6, wherein said determining the three projection surfaces from the X object coordinate information comprises:

constructing a target matrix with X rows and three columns according to the X target coordinate information;

determining three eigenvalues and three eigenvectors after multiplication of a transposed matrix of the target matrix and the target matrix, wherein each eigenvector is a normal vector of each projection surface;

and determining the three projection surfaces according to the three characteristic values, the three characteristic vectors and a plane equation in a three-dimensional space.

8. The method of claim 5, wherein after determining the three projection planes from the X keypoints, the method further comprises:

and determining the regular VOI according to the X key points and the three projection surfaces.

9. The method of claim 8, wherein determining the regular VOI from the X keypoints and the three projection planes comprises:

respectively determining a first distance between each key point in the X key points and a first projection plane, wherein the first projection plane is as follows: any one of the three projection surfaces;

determining a first size parameter of the regular VOI according to a maximum distance of the X first distances, the first size parameter being: any one of the three target size parameters;

determining the regular VOI based on the three target size parameters.

10. A VOI determination apparatus comprising a processor, a memory, and a program or instructions stored on the memory and executable on the processor, the program or instructions when executed by the processor implementing the steps of the VOI determination method of any of claims 1 to 9.